Hyperspectral Image Classification Based on Deep Attention Graph Convolutional Network

• Published in: IEEE transactions on geoscience and remote sensing 2022, Vol.60, p.1-16
• Main Authors: Bai, Jing, Ding, Bixiu, Xiao, Zhu, Jiao, Licheng, Chen, Hongyang, Regan, Amelia C.
• Format: Article
• Language: English
• Subjects: Aggregates; Artificial neural networks; Attention mechanism; Classification; Convolution; Correlation; Data mining; Datasets; Divergence; Feature extraction; graph convolution network (GCN); hyperspectral image classification (HIC); Hyperspectral imaging; Image classification; Kernel; Measurement; Measurement methods; Object recognition; Remote observing; Remote sensing; Similarity; similarity measurement; Spatial resolution; Spectra; Spectral resolution; Training
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2021.3066485

Hyperspectral images (HSIs) have gained high spectral resolution due to recent advances in spectral imaging technologies. This incurs problems, such as an increased data scale and an increased number of bands for HSIs, which results in a complex correlation between different bands. In the applications of remote sensing and earth observation, ground objects represented by each HSI pixel are composed of physical and chemical non-Euclidean structures, and HSI classification (HIC) is becoming a more challenging task. To solve the above problems, we propose a framework based on a deep attention graph convolutional network (DAGCN). Specifically, we first integrate an attention mechanism into the spectral similarity measurement to aggregate similar spectra. Therefore, we propose a new similarity measurement method, i.e., the mixed measurement of a kernel spectral angle mapper and spectral information divergence (KSAM-SID), to aggregate similar spectra. Considering the non-Euclidean structural characteristics of HSIs, we design deep graph convolutional networks (DeepGCNs) as a feature extraction method to extract deep abstract features and explore the internal relationship between HSI data. Finally, we dynamically update the attention graph adjacency matrix to adapt to the changes in each feature graph. Experiments on three standard HSI data sets, namely, the Indian Pines, Pavia University, and Salinas data sets, demonstrate that the DAGCN outperforms the baselines in terms of various evaluation criteria. For example, on the Indian Pines data set, the overall accuracy of the proposed method achieves 98.61% when the training sample is 10%.